© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9074
    Prev
    Next
    INDEX
    Explanations

    topics related to authority, accountability, and social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before a verb of action/consequence

    np_acts-logits-general · gemini-2.0-flash

    harm or destroy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.65
    énario
    -0.57
    UserScript
    -0.56
    enumii
    -0.55
     ***!
    -0.54
    Související
    -0.54
    onViewCreated
    -0.52
     politely
    -0.52
    tikzpicture
    -0.52
    новниш
    -0.50
    POSITIVE LOGITS
     hurt
    1.05
     harm
    1.01
     harmed
    0.97
    hurt
    0.95
     hurting
    0.87
    harmed
    0.86
     harming
    0.82
    harm
    0.80
     harms
    0.79
    Harm
    0.72
    Activations Density 0.352%

    No Known Activations